Model for tracking moving targets using heterogeneous camera systems
MetadataShow full item record
Sufficient camera coverage is critical to the maintenance of the track continuity of a moving target across a large scale surveillance area. Due to economic and bandwidth reasons, it is often not possible to ensure that cameras within a large distributed surveillance system always have overlapping coverage. Traditional tracking schemes that rely on fixed stationary cameras are prone to fail when the non-overlapping coverage between adjacent cameras becomes significant. In this paper, we present a novel approach on building a tracking model that uses heterogeneous camera systems to reduce the non-overlapping problem. We incorporate the surveillance cameras that are installed on public transport vehicles such as buses into the existing distributed camera system to dynamically increase the surveillance space, as when these vehicles move around the surveillance area the on-board cameras act as mobile video sensors. We adopt a grid-based filtering approach together with a road map to systematically integrate the multiple observations coming from the heterogeneous sensors. Simulated experimental results have shown that our approach has the potential to deal with large-scale observations that are prevalent in city-wide implementation.
Showing items related by title, author, creator and subject.
Albrecht, Thomas (2012)Mobile surveillance systems play an important role to minimise security and safety threats in high-risk or hazardous environments. Providing a mobile marine surveillance platform with situational awareness of its environment ...
Nguyen, Nam; Bui, Hung H.; Venkatesh, Svetha; West, Geoffrey (2003)In this paper, we present a distributed surveillance system that uses multiple cheap static cameras to track multiple people in indoor environments. The system has a set of Camera Processing Modules and a Central Module ...
Leoputra, Wilson Suryajaya (2009)Foreground object detection is a fundamental task in computer vision with many applications in areas such as object tracking, event identification, and behavior analysis. Most conventional foreground object detection ...